ext4: main fast-commit commit path

This patch adds main fast commit commit path handlers. The overall
patch can be divided into two inter-related parts:

(A) Metadata updates tracking

    This part consists of helper functions to track changes that need
    to be committed during a commit operation. These updates are
    maintained by Ext4 in different in-memory queues. Following are
    the APIs and their short description that are implemented in this
    patch:

    - ext4_fc_track_link/unlink/creat() - Track unlink. link and creat
      operations
    - ext4_fc_track_range() - Track changed logical block offsets
      inodes
    - ext4_fc_track_inode() - Track inodes
    - ext4_fc_mark_ineligible() - Mark file system fast commit
      ineligible()
    - ext4_fc_start_update() / ext4_fc_stop_update() /
      ext4_fc_start_ineligible() / ext4_fc_stop_ineligible() These
      functions are useful for co-ordinating inode updates with
      commits.

(B) Main commit Path

    This part consists of functions to convert updates tracked in
    in-memory data structures into on-disk commits. Function
    ext4_fc_commit() is the main entry point to commit path.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/20201015203802.3597742-6-harshadshirwadkar@gmail.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 172 insertions, 0 deletions

diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 4c8b99ec8606..521de3a82118 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -95,6 +95,16 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B);
 	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
 	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
+#define show_fc_reason(reason)						\
+	__print_symbolic(reason,					\
+		{ EXT4_FC_REASON_XATTR,		"XATTR"},		\
+		{ EXT4_FC_REASON_CROSS_RENAME,	"CROSS_RENAME"},	\
+		{ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \
+		{ EXT4_FC_REASON_MEM,	"NO_MEM"},			\
+		{ EXT4_FC_REASON_SWAP_BOOT,	"SWAP_BOOT"},		\
+		{ EXT4_FC_REASON_RESIZE,	"RESIZE"},		\
+		{ EXT4_FC_REASON_RENAME_DIR,	"RENAME_DIR"},		\
+		{ EXT4_FC_REASON_FALLOC_RANGE,	"FALLOC_RANGE"})
 
 TRACE_EVENT(ext4_other_inode_update_time,
 	TP_PROTO(struct inode *inode, ino_t orig_ino),
@@ -2791,6 +2801,168 @@ TRACE_EVENT(ext4_lazy_itable_init,
 		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group)
 );
 
+TRACE_EVENT(ext4_fc_commit_start,
+	TP_PROTO(struct super_block *sb),
+
+	TP_ARGS(sb),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+	),
+
+	TP_printk("fast_commit started on dev %d,%d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev))
+);
+
+TRACE_EVENT(ext4_fc_commit_stop,
+	    TP_PROTO(struct super_block *sb, int nblks, int reason),
+
+	TP_ARGS(sb, nblks, reason),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, nblks)
+		__field(int, reason)
+		__field(int, num_fc)
+		__field(int, num_fc_ineligible)
+		__field(int, nblks_agg)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->nblks = nblks;
+		__entry->reason = reason;
+		__entry->num_fc = EXT4_SB(sb)->s_fc_stats.fc_num_commits;
+		__entry->num_fc_ineligible =
+			EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits;
+		__entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks;
+	),
+
+	TP_printk("fc on [%d,%d] nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nblks, __entry->reason, __entry->num_fc,
+		  __entry->num_fc_ineligible, __entry->nblks_agg)
+);
+
+#define FC_REASON_NAME_STAT(reason)					\
+	show_fc_reason(reason),						\
+	__entry->sbi->s_fc_stats.fc_ineligible_reason_count[reason]
+
+TRACE_EVENT(ext4_fc_stats,
+	    TP_PROTO(struct super_block *sb),
+
+	    TP_ARGS(sb),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(struct ext4_sb_info *, sbi)
+		    __field(int, count)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = sb->s_dev;
+		    __entry->sbi = EXT4_SB(sb);
+		    ),
+
+	    TP_printk("dev %d:%d fc ineligible reasons:\n"
+		      "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; "
+		      "num_commits:%ld, ineligible: %ld, numblks: %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
+		      __entry->sbi->s_fc_stats.fc_num_commits,
+		      __entry->sbi->s_fc_stats.fc_ineligible_commits,
+		      __entry->sbi->s_fc_stats.fc_numblks)
+
+);
+
+#define DEFINE_TRACE_DENTRY_EVENT(__type)				\
+	TRACE_EVENT(ext4_fc_track_##__type,				\
+	    TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), \
+									\
+	    TP_ARGS(inode, dentry, ret),				\
+									\
+	    TP_STRUCT__entry(						\
+		    __field(dev_t, dev)					\
+		    __field(int, ino)					\
+		    __field(int, error)					\
+		    ),							\
+									\
+	    TP_fast_assign(						\
+		    __entry->dev = inode->i_sb->s_dev;			\
+		    __entry->ino = inode->i_ino;			\
+		    __entry->error = ret;				\
+		    ),							\
+									\
+	    TP_printk("dev %d:%d, inode %d, error %d, fc_%s",		\
+		      MAJOR(__entry->dev), MINOR(__entry->dev),		\
+		      __entry->ino, __entry->error,			\
+		      #__type)						\
+	)
+
+DEFINE_TRACE_DENTRY_EVENT(create);
+DEFINE_TRACE_DENTRY_EVENT(link);
+DEFINE_TRACE_DENTRY_EVENT(unlink);
+
+TRACE_EVENT(ext4_fc_track_inode,
+	    TP_PROTO(struct inode *inode, int ret),
+
+	    TP_ARGS(inode, ret),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(int, ino)
+		    __field(int, error)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = inode->i_sb->s_dev;
+		    __entry->ino = inode->i_ino;
+		    __entry->error = ret;
+		    ),
+
+	    TP_printk("dev %d:%d, inode %d, error %d",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error)
+	);
+
+TRACE_EVENT(ext4_fc_track_range,
+	    TP_PROTO(struct inode *inode, long start, long end, int ret),
+
+	    TP_ARGS(inode, start, end, ret),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(int, ino)
+		    __field(long, start)
+		    __field(long, end)
+		    __field(int, error)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = inode->i_sb->s_dev;
+		    __entry->ino = inode->i_ino;
+		    __entry->start = start;
+		    __entry->end = end;
+		    __entry->error = ret;
+		    ),
+
+	    TP_printk("dev %d:%d, inode %d, error %d, start %ld, end %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error, __entry->start,
+		      __entry->end)
+	);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */